© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2582
    Prev
    Next
    INDEX
    Explanations

    concepts related to access, communication, and relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "to"

    np_acts-logits-general · gemini-2.0-flash

    followed by to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    to
    -0.92
     untuk
    -0.89
     để
    -0.87
    To
    -0.83
    untuk
    -0.78
    TO
    -0.77
     να
    -0.75
    Чтобы
    -0.73
     чтобы
    -0.73
     To
    -0.73
    POSITIVE LOGITS
     tot
    0.64
    )}_
    0.64
    utilisons
    0.60
     directly
    0.59
    TextSpan
    0.58
    ]>=
    0.57
    oneofs
    0.56
    %";
    0.56
    ratulations
    0.56
    Czytaj
    0.56
    Activations Density 0.600%

    No Known Activations